Abstract: Understanding video is a fundamental skill of intelligent systems such as robots or virtual assistants, to be able to move and interact with the world or with humans. However, learning how to understand video is very expensive, both in terms of data and compute. This cost has a wide range of effects, from carbon emissions to holding back progress in research. In this talk I will discuss the solutions that we are designing in my lab, as well as the underlying principles and takeaway messages for future work in this area.

Title: Towards broader parabolic PDE solvers in geometry processing

(IPAB Workshop): Adaptive Experience Sharing in Multi-Agent Reinforcement Learning: A Unified Approach for Heterogeneous and Homogeneous Agents

Towards multi-intelligences: are we there yet?

The National Robotarium has partnered with Highland and Islands Enterprise for a TechHUB webinar exploring how can benefit the food and drink, and agricultural sectors.

Join the webinar on Monday 16th Sept and learn:

Additive Manufacturing & 3D Printing | CNC Machining | Traditional Production Technologies. We offer world-class support throughout the product development cycle, from innovation to manufacturing. Renowned for producing high performance polymer and metal parts and prototypes to exacting quality standards, Paragon Rapid Technologies is the preferred low volume production partner for thousands of customers across the aerospace, defence, energy, entertainment, automotive, medical, industrial and consumer industries in the UK.

This is a Joint AIAI, ANC, ICSA, ILCC, IPAB, LFCS seminar and Scottish Programming Languages Institute (SPLI) Distinguished Lecture

Groq’s Language Processing Unit (LPU) chips are reshaping the landscape of large language model (LLM) deployment at scale. By prioritizing low latency and high throughput, our hardware and software stack enables rapid and efficient inference, making it ideal for applications where LLMs must be invoked repeatedly by agents e.g. for solving mathematical problems.